Unmanned ship dock intelligent charging system based on artificial intelligence

Abstract

The invention discloses an unmanned ship dock intelligent charging system based on artificial intelligence, and relates to the field of unmanned ship dock intelligent charging, and the system comprises a region division module which is used for dividing an unmanned ship dock charging region into a plurality of regions; the ship type identification module is used for identifying the type of the unmanned ship to be charged through an image identification technology; the charging congestion amount module is used for acquiring the driving amount of the unmanned ship in each channel of the dock and calculating the charging congestion amount of each charging area; the congestion amount correction module is used for dynamically adjusting the charging congestion amount of the charging area; and the dynamic adjustment module is used for dynamically adjusting the driving-in channel and the charging power of the unmanned ship to be charged based on the distributed Actor-Critic model architecture. The system has the advantages that the driving-in channel and the charging power of the unmanned ship to be charged are intelligently regulated and controlled, and the charging adaptability and demand of the dock to different types of unmanned ships are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent charging of unmanned ship docks, and in particular to an intelligent charging system for unmanned ship docks based on artificial intelligence. Background Art

[0002] With the accelerated integration of artificial intelligence and unmanned driving technology, building an intelligent charging solution with autonomous adaptation, high efficiency, safety, and collaborative optimization capabilities has become a key issue to support the large-scale development of the low-altitude economy and intelligent transportation industry. Intelligent charging of unmanned ship docks refers to a technical system that uses modular interfaces, dynamic power distribution and standardized communication protocols to achieve autonomous adaptation, safe and efficient charging of multiple types of unmanned ships, and supports remote monitoring and unmanned operations. Through intelligent power distribution and rapid adjustment of charging channels, the berthing time of unmanned ships can be effectively shortened and the charging efficiency of unmanned ship docks can be improved. At the same time, this technology greatly avoids manual participation, reduces labor costs, reduces the risk of human error, and improves the safety and efficiency of the charging process. However, with the increase in the number and types of unmanned ships, it will become particularly important to dynamically adjust the charging power of unmanned ship docks and reasonably arrange the charging channels of unmanned ships.

[0003] With the continuous expansion of the application scenarios of unmanned ships, the dock is the key infrastructure for its dynamic charging. In order to ensure that the dock can accommodate the intelligent charging of multiple types of unmanned ships, it is necessary to ensure the unification of the communication interface and communication protocol of the two. At the same time, it is necessary to dynamically adjust the charging efficiency of the unmanned ships to avoid charging congestion of unmanned ships. However, the existing technical means lack the ability to identify uncertified unmanned ships, resulting in low universality of unmanned ship charging. At the same time, the lack of the ability to intelligently allocate charging channels and dynamically adjust charging power leads to uneven utilization of charging piles, long waiting times in some areas, and low overall charging efficiency of unmanned ships. Summary of the Invention

[0004] In order to solve the above technical problems, an intelligent charging system for unmanned ship docks based on artificial intelligence is provided. This technical solution solves the problems raised in the above background technology, such as the lack of the ability to identify uncertified unmanned ships, resulting in low universality of unmanned ship charging. At the same time, the lack of the ability to intelligently allocate charging channels and dynamically adjust charging power leads to uneven utilization of charging piles, long waiting times in some areas, and low charging efficiency of the overall unmanned ship.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] An intelligent charging system for unmanned ship docks based on artificial intelligence, comprising:

[0007] An area division module is used to divide the unmanned ship dock charging area into several areas according to the types of unmanned ships currently on the market, and charge different types of unmanned ships respectively;

[0008] A ship type recognition module is used to extract the contour features of various types of unmanned ships currently on the market and identify the type of unmanned ship to be charged through image recognition technology;

[0009] A charging congestion module is used to obtain the number of unmanned ships entering each channel of the dock according to the entry of unmanned ships to be charged, and calculate the charging congestion of each charging area;

[0010] A congestion correction module, which is used to dynamically adjust the charging congestion in the charging area according to the actual remaining power of the unmanned ship to be charged;

[0011] A dynamic adjustment module is used to dynamically adjust the entry channel and charging power of the unmanned ship to be charged based on the distributed actor-critic model architecture according to the charging congestion in each charging area and the type of the newly entered unmanned ship to be charged.

[0012] Preferably, the charging congestion module specifically includes:

[0013] An interface data unit, which is used to obtain the total number of charging interfaces and the number of used charging interfaces in each charging area;

[0014] A power calibration unit, configured to obtain the remaining power and target power of the unmanned vessel to be charged according to the communication protocol of the charging interface;

[0015] A charging power setting unit, configured to set the charging power of the unmanned vessel in standard mode;

[0016] A pre-charging time unit, configured to calculate a pre-charging time of the unmanned vessel to be charged according to the remaining power of the unmanned vessel to be charged and the charging power;

[0017] A remaining power estimating unit, configured to determine an estimated value of the remaining power of the unmanned ships waiting to be charged in the queue based on historical charging data of the unmanned ships and a truncated mean formula;

[0018] An entry amount acquisition unit, configured to acquire the entry amount of unmanned ships in each channel of the dock according to the entry situation of the unmanned ships to be charged;

[0019] The charging congestion amount acquisition unit is used to establish a charging area charging congestion amount evaluation model and calculate the charging congestion amount of each charging area.

[0020] Preferably, the charging congestion evaluation model expression of the charging area is:

[0021]

[0022] Where S is the charging congestion value of the charging area, A is the number of unmanned ships entering the dock channel, G is the total number of charging ports in the charging area, g is the number of charging ports in use in the charging area, and T Q-i is the pre-charging time of the i-th unmanned ship to be charged entering the dock channel, where max{1, Gg} is the time to prevent The denominator is zero. In particular, the above formula is a dimensionless calculation.

[0023] Preferably, the congestion correction module specifically includes:

[0024] An error data unit, the error data unit being used to obtain, through a test experiment, error data between an actual value and an estimated value of the remaining power of the unmanned vessel to be charged and error data between a charging congestion value in the charging area, and to establish an error data set;

[0025] A mapping function unit, the mapping function unit being configured to establish, based on the error data set, a mapping function between the remaining power of the unmanned vessel to be charged and the amount of charging congestion in the charging area;

[0026] a compensation coefficient unit, the compensation coefficient unit being configured to determine a compensation coefficient for a charging congestion amount in the charging area according to an error in a charging congestion amount value in the charging area;

[0027] The congestion correction unit is used to establish a dynamic adjustment model for charging congestion in the charging area, dynamically adjust the charging congestion in the charging area, and improve the calculation accuracy of the charging congestion in the charging area.

[0028] Preferably, the mapping function between the remaining power of the unmanned ship to be charged and the error in charging congestion in the charging area is:

[0029] ΔS=αΔC+β(ΔC) 2

[0030] Where ΔS is the error of the charging congestion value in the charging area, ΔC is the error of the remaining power of the unmanned ship to be charged, α is the linear compensation coefficient, and β is the quadratic linear compensation coefficient, which is used for quadratic correction when the error is large. α and β can be determined by solving the error data set based on the least squares method;

[0031] The compensation coefficient expression of the charging congestion amount in the charging area is:

[0032]

[0033] Where λ is the compensation coefficient of charging congestion in the charging area;

[0034] The dynamic adjustment model expression of charging congestion in the charging area is:

[0035] S 真 =λS

[0036] Where S 真 The charging congestion in the charging area after dynamic adjustment.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention provides an artificial intelligence-based unmanned ship dock intelligent charging system. According to the types of unmanned ships available on the market, the unmanned ship dock charging area is divided into several areas, and a one-to-one correspondence is set between each type of unmanned ship, the charging area, and the independent channel. Thus, through image recognition technology, the identified type of unmanned ship to be charged is guided to the charging channel of each area. Secondly, this solution obtains the charging congestion situation of each charging area by setting a charging congestion module, and dynamically adjusts the charging congestion of the charging area through a congestion correction module to ensure the accuracy of the charging congestion of the charging area. Finally, according to the charging congestion of each charging area and the type of newly entered unmanned ship to be charged, an unmanned ship dock intelligent charging model is constructed based on the distributed actor-critic model architecture. The entry channel and charging power of the unmanned ship to be charged are comprehensively evaluated and dynamically adjusted, thereby intelligently regulating the entry channel and charging power of the unmanned ship to be charged, and improving the adaptability and demand of the dock for charging different types of unmanned ships. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a structural block diagram of an intelligent charging system for an artificial intelligence-based unmanned ship dock according to the present invention;

[0040] Figure 2 This is a flowchart for extracting the contour features of various types of unmanned ships currently on the market and identifying the type of unmanned ship to be charged through image recognition technology;

[0041] Figure 3 This is a flow chart of the present invention for obtaining the number of unmanned ships entering each channel of the dock based on the entry of unmanned ships to be charged, and calculating the charging congestion volume of each charging area;

[0042] Figure 4This is a flow chart of dynamically adjusting the charging congestion in the charging area according to the actual remaining power of the unmanned ship to be charged. DETAILED DESCRIPTION

[0043] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0044] Reference Figure 1 As shown, an intelligent charging system for an unmanned ship dock based on artificial intelligence includes:

[0045] An area division module is used to divide the unmanned ship dock charging area into several areas according to the types of unmanned ships currently on the market, and charge different types of unmanned ships respectively;

[0046] A ship type recognition module is used to extract the contour features of various types of unmanned ships currently on the market and identify the type of unmanned ship to be charged through image recognition technology;

[0047] A charging congestion module is used to obtain the number of unmanned ships entering each channel of the dock according to the entry of unmanned ships to be charged, and calculate the charging congestion of each charging area;

[0048] A congestion correction module, which is used to dynamically adjust the charging congestion in the charging area according to the actual remaining power of the unmanned ship to be charged;

[0049] A dynamic adjustment module is used to dynamically adjust the entry channel and charging power of the unmanned ship to be charged based on the distributed actor-critic model architecture according to the charging congestion in each charging area and the type of the newly entered unmanned ship to be charged.

[0050] Reference Figure 1 As shown, the charging congestion module specifically includes:

[0051] An interface data unit, which is used to obtain the total number of charging interfaces and the number of used charging interfaces in each charging area;

[0052] A power calibration unit, configured to obtain the remaining power and target power of the unmanned vessel to be charged according to the communication protocol of the charging interface;

[0053] A charging power setting unit, configured to set the charging power of the unmanned vessel in standard mode;

[0054] A pre-charging time unit, configured to calculate a pre-charging time of the unmanned vessel to be charged according to the remaining power of the unmanned vessel to be charged and the charging power;

[0055] A remaining power estimating unit, configured to determine an estimated value of the remaining power of the unmanned ships waiting to be charged in the queue based on historical charging data of the unmanned ships and a truncated mean formula;

[0056] An entry amount acquisition unit, configured to acquire the entry amount of unmanned ships in each channel of the dock according to the entry situation of the unmanned ships to be charged;

[0057] The charging congestion amount acquisition unit is used to establish a charging area charging congestion amount evaluation model and calculate the charging congestion amount of each charging area.

[0058] Reference Figure 1 As shown, the congestion correction module specifically includes:

[0059] An error data unit, the error data unit being used to obtain, through a test experiment, error data between an actual value and an estimated value of the remaining power of the unmanned vessel to be charged and error data between a charging congestion value in the charging area, and to establish an error data set;

[0060] A mapping function unit, the mapping function unit being configured to establish, based on the error data set, a mapping function between the remaining power of the unmanned vessel to be charged and the amount of charging congestion in the charging area;

[0061] a compensation coefficient unit, the compensation coefficient unit being configured to determine a compensation coefficient for a charging congestion amount in the charging area according to an error in a charging congestion amount value in the charging area;

[0062] The congestion correction unit is used to establish a dynamic adjustment model for charging congestion in the charging area, dynamically adjust the charging congestion in the charging area, and improve the calculation accuracy of the charging congestion in the charging area.

[0063] It can be explained that with the continuous expansion of the application scenarios of unmanned ships, the dock is the key infrastructure for its dynamic charging. In order to ensure that the dock can accommodate the intelligent charging of multiple types of unmanned ships, it is necessary to ensure the unification of the communication interface and communication protocol of the two. At the same time, it is necessary to dynamically adjust the charging efficiency of the unmanned ship to avoid charging congestion of the unmanned ship. Therefore, this plan divides the unmanned ship dock charging area into several areas according to the types of unmanned ships available on the market, and sets a one-to-one correspondence between each type of unmanned ship and the charging area and independent channel, so that the identified type of unmanned ship to be charged can be guided to the charging channel of each area through image recognition technology. Secondly, this solution obtains the charging congestion situation of each charging area by setting up a charging congestion module, and dynamically adjusts the charging congestion of the charging area through the congestion correction module to ensure the accuracy of the charging congestion of the charging area. Finally, according to the charging congestion of each charging area and the type of new unmanned ships to be charged, an unmanned ship dock intelligent charging model is constructed based on the distributed Actor-Critic model architecture, which comprehensively evaluates and dynamically adjusts the entry channel and charging power of the unmanned ships to be charged, thereby intelligently regulating the entry channel and charging power of the unmanned ships to be charged, and improving the dock's adaptability and demand for charging different types of unmanned ships.

[0064] According to the types of unmanned ships currently available in the market, the unmanned ship dock charging area is divided into several areas, and charging for different types of unmanned ships is carried out separately. Specifically, the following areas are included:

[0065] Based on the types of unmanned ships currently available in the market, the dock charging area for unmanned ships is divided into several areas. The charging areas are mainly divided by the type of unmanned ship, charging interface, and communication protocol.

[0066] According to the division of the unmanned ship dock charging area, independent channels leading to each charging area are set up respectively;

[0067] According to the types of unmanned ships currently available in the market, a one-to-one correspondence is established between each type of unmanned ship and the charging area and independent channel.

[0068] It can be explained that the heterogeneity of the charging interface and the communication protocol causes the system to only be able to recognize pre-certified ship types. During the charging process, many types of unmanned ships cannot be charged or charging is abnormal due to the incompatibility of the communication interface and the protocol. In particular, it is impossible to obtain the charging data information of the unmanned ship to be charged through the communication protocol, where the charging data information includes information on the remaining power, target power and charging efficiency. Therefore, in order to ensure the charging safety of the unmanned ship to be charged, this solution divides the unmanned ship dock charging area according to the types of unmanned ships available on the market, sets up independent channels to each charging area, and establishes a one-to-one correspondence between each type of unmanned ship and the charging area and independent channel, thereby improving the adaptability of the unmanned ship to the charging interface and communication protocol, and further improving the charging safety of the unmanned ship. As the unmanned ship type certification becomes more detailed, the unmanned ship dock charging service will become more universal.

[0069] Reference Figure 2 As shown, the extraction of contour features of various types of unmanned ships currently available on the market and identification of the type of unmanned ship to be charged by image recognition technology specifically include:

[0070] The system collects multi-angle visual data of the external contour features of multiple types of unmanned ships and establishes an unmanned ship recognition image set, which contains the external contour features of unmanned ships under different scenes and lighting conditions;

[0071] Based on the grayscale formula, the images in the unmanned ship recognition image set are grayscaled;

[0072] Based on the filtering algorithm, the images in the grayscale unmanned ship recognition image set are subjected to noise reduction and smoothing processing;

[0073] Based on the image recognition technology of Canny operator edge detection, the external contour features of the unmanned ship to be charged are extracted, and a database of types of unmanned ships to be charged is constructed;

[0074] An image acquisition device is set up to obtain visual data of the unmanned ship to be charged, and the type of the unmanned ship to be charged is identified based on a database of types of the unmanned ship to be charged.

[0075] It can be explained that in the existing technology, it is difficult to identify third-party unmanned ships that are not included in the certification system by using a preset ID or tag for limited authentication, which makes it difficult for third-party unmanned ships to enter the unmanned ship dock for charging, or it is impossible to effectively allocate charging channels for third-party unmanned ships. Therefore, this solution systematically collects multi-angle visual data of the external contour features of multiple types of unmanned ships, establishes an unmanned ship identification image set, and uses the image recognition technology of Canny operator edge detection to extract the external contour features of the unmanned ship to be charged, and constructs a database of types of unmanned ships to be charged. According to the external contour of the unmanned ship to be charged collected by the image acquisition device and the database of types of unmanned ships to be charged, the type of the unmanned ship to be charged is comprehensively judged by point set comparison, thereby completing the type identification of the unmanned ship to be charged, wherein the database of types of unmanned ships to be charged includes: point set coordinates or feature vectors of the contour of the unmanned ship to be charged and associated metadata, such as object category, size, and allowable error range.

[0076] Reference Figure 3 As shown, the method of obtaining the entry volume of unmanned ships in each channel of the dock according to the entry of unmanned ships to be charged and calculating the charging congestion volume in each charging area specifically includes:

[0077] Get the total number of charging ports and the number of used charging ports in each charging area;

[0078] According to the communication protocol of the charging interface, the remaining power and target power of the unmanned ship to be charged are obtained;

[0079] Set the charging power of the unmanned vessel in standard mode;

[0080] Calculating the pre-charging time of the unmanned vessel to be charged according to the remaining power of the unmanned vessel to be charged and the charging power;

[0081] According to the historical charging data of the unmanned ships, the estimated value of the remaining power of the unmanned ships waiting to be charged is determined based on the truncated mean formula;

[0082] According to the entry of unmanned ships to be charged, the number of unmanned ships entering each channel of the dock is obtained;

[0083] Establish a charging congestion assessment model for charging areas and calculate the charging congestion in each charging area;

[0084] The charging congestion evaluation model expression of the charging area is:

[0085]

[0086] Where S is the charging congestion value of the charging area, A is the number of unmanned ships entering the dock channel, G is the total number of charging ports in the charging area, g is the number of charging ports in use in the charging area, and T Q-i is the pre-charging time of the i-th unmanned ship to be charged entering the dock channel, where max{1, Gg} is the time to prevent The denominator is zero. In particular, the above formula is a dimensionless calculation.

[0087] It can be explained that obtaining the amount of charging congestion in each charging area is an important part of dynamically adjusting the entry channels and charging power of unmanned ships to be charged. In particular, with the continuous expansion of the application scenarios of unmanned ships and the increase in the number and types of unmanned ships, the demand for dock charging by unmanned ships has increased. By optimizing the path planning of unmanned ships entering the charging channel and dynamically adjusting the charging power allocation strategy, the efficient coordinated operation of the dock intelligent charging system can be achieved, which will significantly improve the charging resource utilization rate and the overall operational efficiency of the unmanned fleet. This is an important guarantee for improving the healthy development of intelligent charging of unmanned ships in docks. Therefore, this scheme establishes a charging area charging congestion evaluation model to calculate the charging congestion in each charging area, thereby providing important data support for the subsequent dynamic adjustment of the entry channels and charging power of unmanned ships to be charged. Among them,

[0088] The expression for calculating the pre-charging time of the unmanned ship to be charged is:

[0089]

[0090] Where, T BZ is the pre-charging time of the unmanned ship to be charged under standard conditions, T CC is the pre-charging time of the unmanned ship to be charged in the constant current stage, T CV is the pre-charging time of the unmanned ship to be charged in the constant voltage stage, T Z is the total pre-charging time of the unmanned ship to be charged in the dynamic state, C m is the target power, i.e. the power when fully charged, C d is the estimated value of the remaining power of the unmanned ship to be charged, C s is the amount of electricity at the end of the constant current stage, P max is the maximum charging power in the constant current stage, P avg is the average power in the constant voltage stage, η is the charging efficiency of the current type of the unmanned vessel to be charged, and δ is the correction coefficient, which is an empirical coefficient. During the constant voltage stage, the charging power gradually decreases. If the average power is directly used to calculate the time, the actual time required will be underestimated. Therefore, δ needs to be introduced to amplify the calculated value to match the actual charging time. It is usually set to 1.2-1.5;

[0091] Among them, since the charging power may change nonlinearly during the actual charging process, such as constant current first and constant voltage during lithium battery fast charging, the charging time under different states is determined according to the intelligent charging requirements of the electric unmanned ship dock;

[0092] Among them, T Q ∈{T ZB , T Z}, can be selected through piecewise function, such as setting a boundary threshold according to the amount of unmanned ships to be charged in each channel. When the threshold is exceeded, the pre-charging time in the dynamic state is selected, that is, T Z Otherwise, the pre-charge time under standard state is used, that is, T BZ The value of

[0093] The truncated mean formula is:

[0094]

[0095] Where C y is the estimated value of the remaining power of the unmanned ships waiting to be charged in the queue, n is the sample size of the historical charging data, k is the number of extreme data values removed, and c i is the remaining power value of the i-th unmanned ship in the historical charging data;

[0096] Since it is impossible to accurately obtain the remaining power of the unmanned ships waiting to be charged in the queue, it is necessary to introduce the estimated value of the remaining power of the unmanned ships waiting to be charged in the queue when calculating the charging congestion in each charging area, so as to estimate the charging congestion in the charging area. Therefore, this scheme adopts the truncated mean method to obtain the estimated value.

[0097] Reference Figure 4 As shown, the dynamic adjustment of the charging congestion in the charging area according to the actual remaining power of the unmanned ship to be charged specifically includes:

[0098] Through test experiments, we obtain the error data between the actual and estimated remaining power of the unmanned ship to be charged, as well as the error data of the charging congestion value in the charging area, and establish an error data set;

[0099] Based on the error data set, a mapping function is established between the remaining power of the unmanned ship to be charged and the error in the charging congestion in the charging area.

[0100] Determining a compensation coefficient for charging congestion in the charging area based on an error in the charging congestion value in the charging area;

[0101] Establish a dynamic adjustment model for charging congestion in charging areas, dynamically adjust the charging congestion in charging areas, and improve the calculation accuracy of charging congestion in charging areas;

[0102] The mapping function of the remaining power of the unmanned ship to be charged and the error of charging congestion in the charging area is:

[0103] ΔS=αΔC+β(ΔC) 2

[0104] Where ΔS is the error of the charging congestion value in the charging area, ΔC is the error of the remaining power of the unmanned ship to be charged, α is the linear compensation coefficient, and β is the quadratic linear compensation coefficient, which is used for quadratic correction when the error is large. α and β can be determined by solving the error data set based on the least squares method;

[0105] The compensation coefficient expression of the charging congestion amount in the charging area is:

[0106]

[0107] Where λ is the compensation coefficient of charging congestion in the charging area;

[0108] The dynamic adjustment model expression of charging congestion in the charging area is:

[0109] S 真 =λS

[0110] Where S 真 The charging congestion in the charging area after dynamic adjustment.

[0111] It can be explained that since the unmanned ship dock cannot accurately obtain the remaining power of the unmanned ships waiting to be charged in the queue, the remaining power of the unmanned ships to be charged can only be accurately obtained when charging, so the calculated charging congestion amount in the charging area needs to be corrected to ensure its accuracy. Therefore, this scheme obtains the error data between the actual value and the estimated value of the remaining power of the unmanned ships to be charged, and establishes a mapping function of the error between the remaining power of the unmanned ships to be charged and the charging congestion amount in the charging area, thereby reflecting the error data of the charging congestion amount in the charging area, thereby determining the compensation coefficient of the charging congestion amount in the charging area, and establishing a dynamic adjustment model for the charging congestion amount in the charging area, so as to realize dynamic adjustment of the charging congestion amount in the charging area.

[0112] The method of dynamically adjusting the entry channel and charging power of the unmanned vessel to be charged based on the distributed actor-critic model architecture according to the charging congestion level of each charging area and the type of the newly entered unmanned vessel to be charged specifically includes:

[0113] According to the identification results of the new unmanned ship to be charged and the calculation results of the charging congestion in the charging area, the data input quantity of the same sequence is established;

[0114] The calculation result data of the charging congestion amount in the charging area includes: the value of the charging congestion amount in the charging area and the data of each parameter in the dynamic adjustment model of the charging congestion amount in the charging area;

[0115] Set the channel label of each charging area, and use the channel label of the unmanned ship to be charged and the charging power adjustment as output;

[0116] Based on the distributed Actor-Critic model architecture, an intelligent charging model for unmanned ship docks is constructed to comprehensively evaluate and dynamically adjust the entry channel and charging power of the unmanned ship to be charged.

[0117] It can be explained that the distributed Actor-Critic model architecture is a deep reinforcement learning algorithm that combines asynchronous parallel training with the Actor-Critic framework. It aims to accelerate the training process and improve policy stability through distributed computing. Its core architecture includes parallel Worker nodes to generate experience data and global parameter server aggregation learning. This solution uses the type identification results of newly entered unmanned ships to be charged and the calculation results of charging congestion in the charging area as input, and the channel label and charging power adjustment amount of the unmanned ships to be charged as output. Based on the distributed Actor-Critic model architecture, an unmanned ship dock intelligent charging model is constructed. Among them, the network architecture of the unmanned ship dock intelligent charging model includes:

[0118] A graph neural network is used to process input data. It models the charging stations and unmanned boats in each charging area as nodes of the graph, with connections as edges. Through a three-layer attention mechanism, it outputs 256-dimensional node embeddings and generates a global state vector by mean pooling all node embeddings.

[0119] The Actor network outputs the selection probability of each channel through a fully connected layer and a Softmax function, and outputs the charging power adjustment through a fully connected layer and a Sigmoid function.

[0120] The critic network outputs a scalar through the fully connected layer to predict the long-term cumulative reward of the current state;

[0121] The reward function expression is:

[0122]

[0123] Where R t is the reward value for predicting the current state, ω1, ω2, ω3, and ω4 are weight coefficients, f is the number of unmanned ships that have completed charging, F is the total number of unmanned ships that have been charged, and T evg Average waiting time in queue for an unmanned vessel, T 总The total waiting time in queue for the unmanned vessel, is the charging power fluctuation rate of the unmanned ship, L is the conflict allocation indicator function, where

[0124] In summary, the advantages of the present invention are: intelligently regulating the entry channel and charging power of the unmanned ship to be charged, and improving the adaptability and demand of the dock for charging different types of unmanned ships.

[0125] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent charging system for unmanned ship dock based on artificial intelligence, characterized in that: include: An area division module is used to divide the unmanned ship dock charging area into several areas according to the types of unmanned ships currently on the market, and charge different types of unmanned ships respectively; A ship type recognition module is used to extract the contour features of various types of unmanned ships currently on the market and identify the type of unmanned ship to be charged through image recognition technology; A charging congestion module is used to obtain the number of unmanned ships entering each channel of the dock according to the entry of unmanned ships to be charged, and calculate the charging congestion of each charging area; A congestion correction module, which is used to dynamically adjust the charging congestion in the charging area according to the actual remaining power of the unmanned ship to be charged; A dynamic adjustment module is used to dynamically adjust the entry channel and charging power of the unmanned ship to be charged based on the distributed actor-critic model architecture according to the charging congestion in each charging area and the type of the newly entered unmanned ship to be charged.

2. The intelligent charging system for unmanned ship dock based on artificial intelligence according to claim 1 is characterized in that: According to the types of unmanned ships currently available in the market, the unmanned ship dock charging area is divided into several areas, and charging for different types of unmanned ships is carried out separately. Specifically, the following areas are included: Based on the types of unmanned ships currently available in the market, the dock charging area for unmanned ships is divided into several areas. The charging areas are mainly divided by the type of unmanned ship, charging interface, and communication protocol. According to the division of the unmanned ship dock charging area, independent channels leading to each charging area are set up respectively; According to the types of unmanned ships currently available in the market, a one-to-one correspondence is established between each type of unmanned ship and the charging area and independent channel.

3. The intelligent charging system for unmanned ship dock based on artificial intelligence according to claim 2 is characterized in that: The extraction of contour features of various types of unmanned ships currently on the market and identification of the type of unmanned ship to be charged by image recognition technology specifically include: The system collects multi-angle visual data of the external contour features of multiple types of unmanned ships and establishes an unmanned ship recognition image set, which contains the external contour features of unmanned ships under different scenes and lighting conditions; Based on the grayscale formula, the images in the unmanned ship recognition image set are grayscaled; Based on the filtering algorithm, the images in the grayscale unmanned ship recognition image set are subjected to noise reduction and smoothing processing; Based on the image recognition technology of Canny operator edge detection, the external contour features of the unmanned ship to be charged are extracted, and a database of types of unmanned ships to be charged is constructed; An image acquisition device is set up to obtain visual data of the unmanned ship to be charged, and the type of the unmanned ship to be charged is identified based on a database of types of the unmanned ship to be charged.

4. The intelligent charging system for an unmanned ship dock based on artificial intelligence according to claim 3 is characterized in that: The charging congestion module specifically includes: An interface data unit, which is used to obtain the total number of charging interfaces and the number of used charging interfaces in each charging area; A power calibration unit, configured to obtain the remaining power and target power of the unmanned vessel to be charged according to the communication protocol of the charging interface; A charging power setting unit, configured to set the charging power of the unmanned vessel in standard mode; A pre-charging time unit, configured to calculate a pre-charging time of the unmanned vessel to be charged according to the remaining power of the unmanned vessel to be charged and the charging power; A remaining power estimating unit, configured to determine an estimated value of the remaining power of the unmanned ships waiting to be charged in the queue based on historical charging data of the unmanned ships and a truncated mean formula; An entry amount acquisition unit, configured to acquire the entry amount of unmanned ships in each channel of the dock according to the entry situation of the unmanned ships to be charged; The charging congestion amount acquisition unit is used to establish a charging area charging congestion amount evaluation model and calculate the charging congestion amount of each charging area.

5. The intelligent charging system for an artificial intelligence unmanned ship dock according to claim 4 is characterized in that: The charging congestion evaluation model expression of the charging area is: Where S is the charging congestion value of the charging area, A is the number of unmanned ships entering the dock channel, G is the total number of charging ports in the charging area, g is the number of charging ports in use in the charging area, and T Q-i is the pre-charging time of the i-th unmanned ship to be charged entering the dock channel, where max{1, Gg} is the time to prevent The denominator is zero. In particular, the above formula is a dimensionless calculation.

6. The intelligent charging system for an artificial intelligence unmanned ship dock according to claim 5 is characterized in that: The congestion correction module specifically includes: An error data unit, the error data unit being used to obtain, through a test experiment, error data between an actual value and an estimated value of the remaining power of the unmanned vessel to be charged and error data between a charging congestion value in the charging area, and to establish an error data set; A mapping function unit, the mapping function unit being configured to establish, based on the error data set, a mapping function between the remaining power of the unmanned vessel to be charged and the amount of charging congestion in the charging area; a compensation coefficient unit, the compensation coefficient unit being configured to determine a compensation coefficient for a charging congestion amount in the charging area according to an error in a charging congestion amount value in the charging area; The congestion correction unit is used to establish a dynamic adjustment model for charging congestion in the charging area, dynamically adjust the charging congestion in the charging area, and improve the calculation accuracy of the charging congestion in the charging area.

7. The intelligent charging system for an artificial intelligence unmanned ship dock according to claim 6 is characterized in that: The mapping function of the remaining power of the unmanned ship to be charged and the error of charging congestion in the charging area is: ΔS=αΔC+β(ΔC) 2 Where ΔS is the error of the charging congestion value in the charging area, ΔC is the error of the remaining power of the unmanned ship to be charged, α is the linear compensation coefficient, and β is the quadratic linear compensation coefficient, which is used for quadratic correction when the error is large. α and β can be determined by solving the error data set based on the least squares method; The compensation coefficient expression of the charging congestion amount in the charging area is: Where λ is the compensation coefficient of charging congestion in the charging area; The dynamic adjustment model expression of charging congestion in the charging area is: S 真 =λS Where S 真 The charging congestion in the charging area after dynamic adjustment.

8. The intelligent charging system for an artificial intelligence unmanned ship dock according to claim 7 is characterized in that: The method of dynamically adjusting the entry channel and charging power of the unmanned vessel to be charged based on the distributed actor-critic model architecture according to the charging congestion level of each charging area and the type of the newly entered unmanned vessel to be charged specifically includes: According to the identification results of the new unmanned ship to be charged and the calculation results of the charging congestion in the charging area, the data input quantity of the same sequence is established; The calculation result data of the charging congestion amount in the charging area includes: the value of the charging congestion amount in the charging area and the data of each parameter in the dynamic adjustment model of the charging congestion amount in the charging area; Set the channel label of each charging area, and use the channel label of the unmanned ship to be charged and the charging power adjustment as output; Based on the distributed Actor-Critic model architecture, an intelligent charging model for unmanned ship docks is constructed to comprehensively evaluate and dynamically adjust the entry channel and charging power of the unmanned ship to be charged.

Images